Triple

T18790349
Position Surface form Disambiguated ID Type / Status
Subject Lille town hall E459495 entity
Predicate usedBy P260 FINISHED
Object Mayor of Lille NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mayor of Lille | Statement: [Lille town hall, usedBy, Mayor of Lille]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mayor of Lille
Context triple: [Lille town hall, usedBy, Mayor of Lille]
  • A. Mayor of Lille chosen
    The Mayor of Lille is the chief elected official responsible for governing and administrating the city of Lille in northern France.
  • B. Mayor of Lyon
    The Mayor of Lyon is the elected head of the municipal government of Lyon, one of France’s largest and most historically significant cities.
  • C. Mayor of Mons
    The Mayor of Mons is the chief elected official responsible for governing the Belgian city of Mons in the Walloon region.
  • D. Mayor of Nice
    The Mayor of Nice is the elected head of the municipal government responsible for leading the administration and representing the French city of Nice.
  • E. Mayor of Neuilly-sur-Seine
    The Mayor of Neuilly-sur-Seine is the chief elected official responsible for governing the affluent suburban commune of Neuilly-sur-Seine, just west of central Paris.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8d396f54c8190ba49db31e8743842 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5978599008190aaceaff1b1e0a2c7 completed April 20, 2026, 3:03 a.m.
Created at: April 10, 2026, 11:53 a.m.